AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Transformers Can Learn Posterior Predictive Distributions In-Context

Gyeonghun Kang, Changwoo J. Lee, Xiang Cheng

ICML 2026 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Approximate inference in Bayesian neural networks · 0 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add attention normalization to the transformer (ablation)GP regression PFN transformer (L=32, C=256) · RBF regression n-generalization (d=8)TV distanceImproved
increase attention depth L (ablation)GP regression PFN transformer · BLR and RBF regressionTV distanceImproved
increase output bin resolution C (ablation)GP regression PFN transformer · BLR and RBF regressionTV distanceImproved
increase pretraining range n_max and depth L (ablation)normalized PFN transformer · RBF regression n-generalization (d=16)prediction error, coverage, TVImproved
increase evaluation sample size n' beyond pretraining range at fixed L and n_max (ablation)finite-iteration solver transformer · RBF regression (d=16)solver errorHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy